# Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.18849 · HTML: https://mlsanity.com/paper/2510.18849/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning](https://mlsanity.com/paper/2506.01347/) (2025)
- [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](https://mlsanity.com/paper/2311.09528/) (2023)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [Personalizing Dialogue Agents via Meta-Learning](https://mlsanity.com/paper/1905.10033/) (2019)
- [Exploiting Persona Information for Diverse Generation of Conversational Responses](https://mlsanity.com/paper/1905.12188/) (2019)
- [SALMON: Self-Alignment with Instructable Reward Models](https://mlsanity.com/paper/2310.05910/) (2023)
- [LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination](https://mlsanity.com/paper/2309.11696/) (2023)
- [PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data](https://mlsanity.com/paper/2502.20616/) (2025)
- [Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona](https://mlsanity.com/paper/2305.11482/) (2023)
- [Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment](https://mlsanity.com/paper/2505.15456/) (2025)
- [HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks](https://mlsanity.com/paper/2503.04378/) (2025)
- [PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization](https://mlsanity.com/paper/2506.12915/) (2025)
- [Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study](https://mlsanity.com/paper/2506.04913/) (2025)
- [Learning from Natural Language Feedback for Personalized Question Answering](https://mlsanity.com/paper/2508.10695/) (2025)

## Built on by (most cited first, 3 of 3)

- [PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory](https://mlsanity.com/paper/2512.06688/) (2025)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization](https://mlsanity.com/paper/2602.11351/) (2026)

## Abstract (arXiv)

Faithfully personalizing large language models (LLMs) to align with individual user preferences is a critical but challenging task. While supervised fine-tuning (SFT) quickly reaches a performance plateau, standard reinforcement learning from human feedback (RLHF) also struggles with the nuances of personalization. Scalar-based reward models are prone to reward hacking which leads to verbose and superficially personalized responses. To address these limitations, we propose Critique-Post-Edit, a robust reinforcement learning framework that enables more faithful and controllable personalization. Our framework integrates two key components: (1) a Personalized Generative Reward Model (GRM) that provides multi-dimensional scores and textual critiques to resist reward hacking, and (2) a Critique-Post-Edit mechanism where the policy model revises its own outputs based on these critiques for more targeted and efficient learning. Under a rigorous length-controlled evaluation, our method substantially outperforms standard PPO on personalization benchmarks. Personalized Qwen2.5-7B achieves an average 11% win-rate improvement, and personalized Qwen2.5-14B model surpasses the performance of GPT-4.1. These results demonstrate a practical path to faithful, efficient, and controllable personalization.